Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    managing finances and security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蛯
    0.50
     beeindruck
    0.50
     convincingly
    0.49
    鄭
    0.49
     immensely
    0.48
    溅
    0.47
    COMANDA
    0.47
     eigenlijk
    0.47
    ﻡ
    0.46
    Hostname
    0.46
    POSITIVE LOGITS
     administrators
    0.49
    aires
    0.48
    tic
    0.48
     pai
    0.45
    tid
    0.44
    a
    0.44
    ه
    0.44
    getCode
    0.43
    머니
    0.43
     administrator
    0.43
    Act Density 0.001%

    No Known Activations